• Paul Bakaus argues that banning an overused AI-design pattern doesn't produce originality — it just relocates the model to the next-nearest cluster in latent space, since 'slop is a moving target' driven by the model's statistical median.
• One technique: run two sub-agents blind to each other's work, one as design director and one as a deterministic linter, because a single agent grading its own output tends to just say it did well.
• Another technique forces divergence by having the model name its top three font choices, then discarding all three to avoid the 'safe prediction' each one represents.
• Bakaus recommends emitting instructions on stdout rather than burying them in prose, since models follow structured output more reliably — though this comes at the cost of losing prompt caching.
• The underlying discipline across all nine techniques: enforce with hooks that block a bad write outright rather than complaining after the fact, because 'if a gate can be skipped, it will be.'

• agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
• subagent — A separate agent spawned by another to do one scoped piece of work in its own context, returning only the result.
• structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
• prompt caching — Reusing the model's processed form of a repeated prompt prefix so subsequent calls skip re-reading it, cutting cost and latency substantially.

• videoOperating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta
• videoVertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave
• videoAre LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google
• videoRouting LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAI

• videoDesign at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.AI Engineer
• videoAI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlackAI Engineer
• videoHarness Engineering is not Enough: Why Software Factories Fail — Dex Horthy, HumanLayerAI Engineer

Checking sign-in…

Loading comments…